figdeck: Instructions file for Claude Code

CLAUDE.md

figdeck CLAUDE.md is an instructions file for Claude Code from 7nohe/figdeck. It costs 3,947 tokens per session, scanned A, original, MIT.

A project instruction file for Figdeck, a tool that turns Markdown files into Figma Slides through a command-line program and a Figma plugin.

In plain words
What is it for?
Use it when installing dependencies, building the CLI or plugin, serving Markdown slide files over WebSocket, running development watchers, checking types, linting, formatting, or testing.
Why use it?
It explains how the project is organized and which commands agents should use to build, run, test, and format it.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is 7nohe/figdeck's own configuration. It tells Claude Code how to work on figdeck itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything figdeck configures →

Reuse

Borrowing it

Nothing to install: this file belongs to 7nohe/figdeck. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/7nohe/figdeck/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/7nohe/figdeck

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for figdeck CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/7nohe/figdeck/claude-md/github.svg)](https://agentmods.dev/instructions/7nohe/figdeck/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/7nohe/figdeck/claude-md"><img src="https://agentmods.dev/badge/instructions/7nohe/figdeck/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for figdeck CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/7nohe/figdeck/claude-md"><img src="https://agentmods.dev/badge/instructions/7nohe/figdeck/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,947 This file is loaded in full into every session.
When invoked 3,947 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.03947 $0.03947
Opus 5.5 $0.01579 $0.01579
Sonnet 5.5 $0.00789 $0.00789
Haiku 4.5 $0.00395 $0.00395

Measured 2mo ago against content hash 17058f1c9bbc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

figdeck CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 414 lines

How it starts

The opening of the file, as written. The whole thing — 414 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

figdeck converts Markdown files into Figma Slides via a CLI + Figma Plugin architecture. The CLI parses Markdown, starts a WebSocket server, and the Figma Plugin connects as a client to receive slide data and generate slides using figma.createSlide().

Build Commands

# Install dependencies
bun install

# Build all packages
bun run build

# Build CLI only
cd packages/cli && bun run build

# Build Plugin only
cd packages/plugin && bun run build

# Watch mode for CLI development
cd packages/cli && bun run dev

Running

# Initialize a new slides.md template with all syntax examples
bun run packages/cli/dist/index.js init
bun run packages/cli/dist/index.js init -o my-slides.md  # custom filename
bun run packages/cli/dist/index.js init --force          # overwrite existing

# WebSocket mode: Start CLI server (waits for Plugin connection on port 4141)
# Watch mode is enabled by default - auto-reloads on file changes
bun run packages/cli/dist/index.js serve examples/sample.md

# WebSocket options (default host is 127.0.0.1 for security)
bun run packages/cli/dist/index.js serve slides.md --host 127.0.0.1 --port 4141

# Disable watch mode
bun run packages/cli/dist/index.js serve slides.md --no-watch

# Remote access (requires explicit flag for non-loopback hosts)
bun run packages/cli/dist/index.js serve slides.md --host 0.0.0.0 --allow-remote

# Authentication (auto-generated secret shown in CLI output for remote connections)
bun run packages/cli/dist/index.js serve slides.md --secret my-secret

# JSON output mode: Parse Markdown and output JSON (no server)
bun run packages/cli/dist/index.js build examples/sample.md              # stdout
bun run packages/cli/dist/index.js build examples/sample.md -o out.json  # file

Architecture

CLI (WebSocket Server)  <--->  Figma Plugin (WebSocket Client)
      port 4141                      ui.html connects

Read the full file on GitHub · 414 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 414 lines · 3,947 tokens per session scan A 17058f1c9bbc

Subscribe to this mod's changes

figdeck CLAUDE.md is an instructions file published in the GitHub repository 7nohe/figdeck (4 stars, last pushed 10mo ago), licensed MIT. It adds 3,947 tokens to every session, about $0.0158 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

figdeck CLAUDE.md compared with instructions from other repositories

figdeck CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
figdeck CLAUDE.md7nohe/figdeckInstructions file410mo agoMITA3,947Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode